awesome-docs

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to save and report single-line, copy-pasteable commands (update docs/常用命令.txt and "report key command" in final responses) which would cause the LLM to include any embedded credentials (API keys, tokens, passwords) verbatim if present, creating an exfiltration risk.